Added groupwiseconv and modified depthwise conv for common interface #948
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Added groupwiseconv and modified depthwise conv for common interface
arhik
commented
Nov 30, 2019
src/layers/conv.jl
Outdated
| @@ -51,6 +51,7 @@ function (c::Conv)(x::AbstractArray) | |||
| # TODO: breaks gpu broadcast :( | |||
| # ndims(x) == ndims(c.weight)-1 && return squeezebatch(c(reshape(x, size(x)..., 1))) | |||
| σ, b = c.σ, reshape(c.bias, map(_->1, c.stride)..., :, 1) | |||
| @show b | |||
|
Looking forward to this! Thanks |
using only ConvDims for all convolutions.
|
Following the breadcrumbs so this issue stays updated, per JuliaGPU/CuArrays.jl#523 (comment) NNlib needs updating before we can revisit a layer in Flux. |
|
As of #1531, grouped convolutions are now possible with |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I am trying to add
groupcountas a member for drafted changes here ->FluxML/NNlib.jl#146 (comment)
In short I am following @staticfloat 's suggestion here JuliaGPU/CuArrays.jl#388 (comment)